Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or criminal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, suggesting a focus on the conclusion of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.77
    agar
    -0.75
    boro
    -0.73
    erville
    -0.68
     proced
    -0.63
     Rebell
    -0.62
    ocial
    -0.61
     ¯
    -0.60
     Alphabet
    -0.60
     Quit
    -0.60
    POSITIVE LOGITS
    Among
    0.74
    Yesterday
    0.73
    Actor
    0.73
    Asked
    0.73
    Specifically
    0.72
    NPR
    0.72
    Eight
    0.72
    WHO
    0.71
    Earlier
    0.71
    Exc
    0.71
    Act Density 0.279%

    No Known Activations